US8224106B2 - Image enhancement system and method using automatic emotion detection - Google Patents
Image enhancement system and method using automatic emotion detection Download PDFInfo
- Publication number
- US8224106B2 US8224106B2 US12/166,676 US16667608A US8224106B2 US 8224106 B2 US8224106 B2 US 8224106B2 US 16667608 A US16667608 A US 16667608A US 8224106 B2 US8224106 B2 US 8224106B2
- Authority
- US
- United States
- Prior art keywords
- image
- parameter
- input image
- score
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 230000008451 emotion Effects 0.000 title abstract description 18
- 230000002996 emotional effect Effects 0.000 claims abstract description 123
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 11
- 230000000704 physical effect Effects 0.000 claims description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006397 emotional response Effects 0.000 description 1
- 230000003054 hormonal effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001404 mediated effect Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/44—Receiver circuitry for the reception of television signals according to analogue transmission standards
- H04N5/57—Control of contrast or brightness
Definitions
- aspects of the present invention relate to an image enhancement system and method using an automatic emotion detection, and more particularly, to an image enhancement system and method that detects an emotional scale using a Z score with respect to an image parameter of an image, selects an image mode according to the emotional scale, and thereby enhances a quality of the image.
- an image reproduction apparatus reproduces various kinds of images that evoke an emotional response from a viewer. For example, fun images can evoke a positive emotion and scary images can evoke a negative emotion.
- Emotion is a physical and/or a mental response unconsciously triggered by the mind. Emotion can be referred to as a complex set of interactions among subjective and objective factors, mediated by neural and/or hormonal systems, which can give rise to affective pleasant or unpleasant experiences.
- the image reproduction apparatus defines genres of categorized images, and optimal settings for each genre is manually adjusted by a user, resulting in an inconvenience to the user. Also, when an undifferentiated setting with respect to an identical genre is applied, an image factor represented by a particular scene cannot be reflected. Accordingly, there is a need for a new image enhancement system and method.
- aspects of the present invention provide an image enhancement system and method that automatically detect an emotion using a Z score with respect to an image parameter of an input image, and thereby can efficiently reflect an emotion caused by an image.
- aspects of the present invention also provide an image enhancement system and method that calculates an emotional scale using a Z score, which is statistical data of an image to objectively apply an emotion to image enhancement.
- aspects of the present invention also provide an image enhancement system and method that selects an image mode according to an emotional scale, adjusts an image factor according to the selected image mode, and thereby can correspond to a mode of an input image.
- aspects of the present invention also provide an image enhancement system and method that calculates one or more image parameters, applies the image parameters to image enhancement, and thereby can accurately reflect an emotion using the image parameters.
- an image enhancement system to adjust an input image according to an emotional scale of the input image
- the image enhancement system including: an emotional scale detection unit to analyze a pixel value of one or more frames of the input image in order to automatically detect the emotional scale of the input image; and an image enhancement unit to enhance a quality of the input image based on an image mode selected according to the emotional scale.
- the emotional scale detection unit may include: an image parameter calculation unit to calculate at least one image parameter using the pixel value; and a Z score computation unit to compute a Z score of each of the at least one image parameter using image statistical data.
- the image parameter calculation unit may perform a color space conversion on the pixel value of the input image according to an image parameter, of the at least one image parameter, to be calculated.
- the image enhancement unit may include: an image mode selection unit to select an image mode of the input image according to the emotional scale; and an image factor adjustment unit to adjust an image factor of the input image based on an image factor adjustment parameter according to the image mode.
- an image enhancement method to adjust an input image according to an emotional scale of the input image, the method including: analyzing a pixel value of one or more frames of the input image in order to automatically detect the emotional scale of the input image; and enhancing a quality of the input image based on an image mode selected according to the emotional scale.
- the detecting of the emotional scale may include: calculating at least one image parameter using the pixel value; and computing a Z score of each of the at least one image parameter using image statistical data.
- the enhancing of the quality of the input image may include: selecting an image mode of the input image according to the emotional scale; and adjusting an image factor of the input image based on an image factor adjustment parameter according to the image mode.
- an image enhancement system to adjust an input image according to an emotional scale of the input image
- the image enhancement system including: an image parameter calculation unit to calculate at least one image parameter using a pixel value of an input image; a Z score computation unit to compute a Z score of each of the at least one image parameter using image statistical data; an image mode selection unit to select an image mode of the input image according to the emotional scale detected using the Z score; and an image factor adjustment unit to adjust an image factor of the input image based on an image factor adjustment parameter according to the image mode.
- an image enhancement method to adjust an input image according to an emotional scale of the input image including: calculating at least one image parameter using a pixel value of an input image; computing a Z score of each of the at least one image parameter using image statistical data; selecting an image mode of the input image according to the emotional scale detected using the Z score; and adjusting an image factor of the input image based on an image factor adjustment parameter according to the image mode.
- an image enhancement system to adjust an input image
- the image enhancement system including: an emotional scale detection unit to automatically detect an emotional scale of the input image; and an image enhancement unit to enhance a quality of the input image according to the emotional scale.
- an image enhancement method to adjust an input image including: automatically detecting an emotional scale of the input image; and enhancing a quality of the input image according to the emotional scale.
- FIG. 1 illustrates an image enhancement system using automatic emotion detection according to an embodiment of the present invention
- FIG. 2 illustrates an emotional scale detection unit of the image enhancement system of FIG. 1 ;
- FIG. 3 illustrates an image enhancement unit of the image enhancement system of FIG. 1 ;
- FIG. 4 illustrates an example of image parameters according to an embodiment of the present invention.
- FIG. 5 illustrates an image enhancement method using automatic emotion detection according to an embodiment of the present invention.
- FIG. 1 illustrates an image enhancement system 101 using automatic emotion detection according to an embodiment of the present invention.
- the image enhancement system 101 includes an emotional scale detection unit 102 and an image enhancement unit 103 .
- the emotional scale detection unit 102 analyzes a pixel value of each frame of an input image and automatically detects an emotional scale of the input image. For example, according to aspects of the present invention, the emotional scale detection unit 102 analyzes a pixel value included in a single scene of an image and automatically detects an emotional scale of the scene.
- the emotional scale is emotional category data to identify at least one emotion. That is, the emotional scale can be mathematical data that represents an emotion caused by the single scene of the input image. Also, the emotional scale can be detected through an image parameter calculated using the pixel value of each of the frames of the input image.
- Emotional category labels can be classified into a positive emotional label and a negative emotional label.
- the positive emotional label includes amusement, happiness, excitement, interest, desire, curiosity, peacefulness, affection, etc.
- the negative emotional label includes fear, sadness, disgust, anger, pity, scare, shock, etc.
- the image enhancement unit 103 enhances a quality of the input image based on an image mode selected according to the emotional scale. That is, the image enhancement unit 103 selects the image mode according to the emotional scale, and adjusts an image factor according to the image mode to thereby enhance the quality of the image.
- the emotional scale detection unit 102 and the image enhancement unit 103 are described in greater detail with reference to FIGS. 2 and 3 , respectively.
- FIG. 2 illustrates the emotional scale detection unit 102 of the image enhancement system 101 of FIG. 1 .
- the emotional scale detection unit 102 includes an image parameter calculation unit 201 and a Z score computation unit 202 .
- the image parameter calculation unit 201 calculates at least one image parameter using a pixel value of an input image.
- the image parameter can be a mathematical parameter representing a physical property of each frame of the input image.
- the image parameter calculation unit 201 may calculate more than one image parameter, configured as a set of parameters (including, for example, an average luminance, Fourier spectrum, etc.).
- the at least one image parameter can be calculated using pixel values of a Red, Green, Blue (RGB) color space.
- RGB Red, Green, Blue
- the at least one image parameter can be calculated using pixel values of YCbCr, Hue, Saturation, Value (HSV), sRGB, CIECAM02, CIEL*a*b, CIEXYZ, or YUV color spaces.
- the image parameter calculation unit 201 can calculate the image parameter, V 1 , V 2 . . . V n using the pixel value of the input image.
- the image parameter calculation unit 201 may perform a color space conversion with respect to the pixel value of the input image according to an image parameter to be calculated. Specifically, the image parameter calculation unit 201 may perform a color space conversion from the RGB color space to the YCbCr, HSV, sRGB, CIECAM02, CIEL*a*b, CIEXYZ, and YUV color space according to the image parameter to be calculated.
- a type of image parameter and a calculation algorithm are described in detail with reference to FIG. 4 .
- the Z score computation unit 202 computes a Z score of each image parameter using image statistical data about a plurality of genres.
- the Z score computation unit 202 can compute the Z score using an average and a standard deviation of an image parameter of various images.
- the Z score indicates a standard score used for a statistical analysis.
- the image statistical data is based on a standard normal distribution.
- the Z score can be computed according to Equation 1:
- Z j denotes a Z score with respect to each image parameter
- V j denotes each computed image parameter
- V j — mean and V j — stdev denote image statistical data that statistically represents the image parameter of various images.
- V j — mean and V j — stdev denote the average and the standard deviation of the image parameter, respectively.
- V j — mean and V j — stdev may be statistical data previously extracted through a plurality of images with respect to a corresponding image parameter.
- V j — mean and V j — stdev can be stored in an emotional scale database 203 in advance and used when computing the Z score.
- each of the image parameters, V 1 , V 2 . . . V n calculated by the image parameter calculation unit 201 corresponds to Z scores, Z 1 , Z 2 . . . Z n .
- the emotional scale detection unit 102 detects an emotional scale of the input image using the computed Z score and a Z score of an image parameter with respect to at least one predetermined emotional scale. For example, the emotional scale detection unit 102 may detect the emotional scale of the input image according to Equation 2:
- Z j denotes the computed Z score
- D k which is an emotional scale, denotes a Euclidean distance of Z j .
- the emotional scale detection unit 102 determines a difference between the computed Z score and the average Z score of each of the image parameters with respect to the at least one predetermined emotional scale, and detects an emotional scale having a minimum difference as the emotional scale of the input image. That is, the emotional scale k having D k corresponding to the minimum difference is detected as the emotional scale of the input image.
- a computed Z score is 3.5 when an average Z score of each image parameter representing happiness, tiresomeness, shock, sadness, anger, and amusement is 1, 8, 10, 4, 7, and 3. Accordingly, the emotional scale detection unit 102 detects an emotional scale of an input image as amusement.
- FIG. 3 illustrates the image enhancement unit 103 of the image enhancement system 101 of FIG. 1 .
- the image enhancement unit 103 includes an image mode selection unit 301 and an image factor adjustment unit 302 .
- the image mode selection unit 301 selects an image mode of an input image according to an emotional scale. For example, any one of various emotions can be selected with respect to a particular scene of the input image according to the emotional scale.
- the image factor adjustment unit 302 adjusts an image factor of the input image using an image factor adjustment parameter according to the image mode.
- the image factor adjustment parameter can have a ( ⁇ ) value and a (+) value, and indicate a constant of a predetermined range.
- the image factor can include lightness, contrast, and saturation, though aspects of the present invention are not limited thereto. That is, the above-described image factor is simply an example, and can vary according to a configuration of the system 101 .
- the image factor adjustment unit 302 may adjust a contrast, which is the image factor of the input image in the present example, according to Equation 3:
- dac out tan ⁇ ( ⁇ 400 ⁇ p + ⁇ 4 ) ⁇ ( dac in - M lum ′ ) + M lum ′ , [ Equation ⁇ ⁇ 3 ]
- dac out and dac in denote any one of an output and input RGB of a current pixel
- M lum ′ denotes a corrected average luminance value.
- dac out is less than 0, (for example, ⁇ 2) dac out may be set as 0.
- dac out is greater than 255, (for example, 260) dac out may be set as 255.
- dac out is from 0 to 255, dac out may be maintained as is.
- Each constant can vary according to the configuration of the system 101 .
- dac out is less than 0, dac out can be set as 0.
- dac out is greater than 255, dac out can be set as 255.
- dac out is from 0 to 255, dac out can be maintained as is.
- the image factor adjustment unit 302 may adjust a saturation, which is the image factor of the input image in the present example, according to Equation 5:
- p denotes the image factor adjustment parameter
- dac rgb denotes a value of each of the R, G, and B.
- Each constant can vary according to the configuration of the system 101 .
- an operation of adjusting the saturation can vary according to the p value.
- FIG. 4 illustrates an example of image parameters according to an embodiment of the present invention.
- the image parameter calculation unit 201 calculates at least one image parameter using a pixel value of an input image.
- the image parameters illustrated in FIG. 4 are simply an example, and can vary according to a type of the system 101 .
- a method of calculating an image parameter is not limited to the following described method.
- V 1 to V 15 of FIG. 4 correspond to image parameters, V 1 , V 2 . . . V n , calculated by the image parameter calculation unit 201 .
- the method of calculating an image parameter of FIG. 4 is described in detail.
- the image parameter calculation unit 201 can compute an average luminance as an image parameter using Equation 6:
- M lum denotes the average luminance
- n and m denote width and length of an image, respectively
- i and j denote a horizontal location and a vertical location of a pixel, respectively
- Y is a value where an R, G, B value of the input image is converted into a luminance value
- a, b, c, and d are constants.
- the image parameter calculation unit 201 can compute a noisiness as an image parameter using Equation 7:
- the image parameter calculation unit 201 can compute an average saturation as an image parameter using Equation 8:
- M sat denotes the average saturation for each frame of the input image
- n and m denote the width and length of the image, respectively
- i and j denote the horizontal location and vertical location of a pixel, respectively
- S denotes a saturation value of a pixel located in (i, j).
- the image parameter calculation unit 201 can compute a color balance as an image parameter using Equation 11:
- the color balance indicates a color temperature closest to an average chromaticity (x, y), after mathematically averaging CIE 1931 tristmulus values of pixels using an sRGB color space conversion.
- p denotes an R, G, B value of an input pixel
- a, b, c, d, e, f, g, h, and i denote constants.
- a, b, c, d, e, f, g, h, and i can be 41.24, 35.76, 18.05, 21.26, 71.52, 7.22, 1.93, 11.92, and 95.05, respectively.
- P denotes an average X, Y, and Z of an input image having a size of n*m
- t denotes a current color temperature of the input image.
- the color temperature of the input image is used to satisfy Equation 12:
- a highly chromatic area with respect to an input image having a high input value can be shown.
- a chromatic highlight may be calculated as follows:
- a histogram of each channel of the R, G, B of the input image is built.
- a binary image (B & W image) is created where white pixels are the pixels extracted in operation (2), and the remaining pixels are black.
- a size of a white object in the binary image is measured.
- Highlights can be shown in an image having a high input value.
- the highlights may be obtained as follows:
- a histogram of each channel of the R, G, B of the input image is built.
- a binary image (B & W image) is created where white corresponds to the pixels in the top 1% of all channels and black corresponds to a rest.
- a vertical and horizontal standard deviation (STD) of white pixels in the binary image are determined.
- An STD value of STD ⁇ square root over (STD ver 2 +STD hor 2 ) ⁇ is returned, where STD ver denotes the vertical STD, and STD hor denotes the horizontal STD.
- An STD value is 0 when a white area is less than 1% of the entire image.
- a discrete cosine transformation (DCT) with respect to each of the R, G, and B channels of the input image is performed.
- DCT discrete cosine transformation
- a high frequency area is omitted in the input image.
- the image parameter calculation unit 201 can compute the sharpness as an image parameter according to Equation 13:
- D sh c size DCT - c ⁇ 100 ⁇ % , [ Equation ⁇ ⁇ 13 ] where c denotes a number of high frequency components in the DC transformed image from among each pixel of the input image, the number of high frequency components is greater than 32, and size DCT denotes a size of the DC transformed image.
- a sharpness block represents a relationship of a blurred and sharp area.
- the sharpness block can be computed as an image parameter according to Equation 14:
- N shb N sh N bl ⁇ 100 ⁇ % , [ Equation ⁇ ⁇ 14 ] where N sh denotes a number of sharp segments, and N bi denotes a number of blurred segments. For example, an image can be segmented into a segment of n*n size.
- a speed of darkening/lightening indicates a change rate of a light and dark area.
- the speed of darkening/lightening can be computed as an image parameter according to Equation 15:
- m′(i) denotes a numerical derivative of m(i)
- i denotes a number of samples in a clip
- n denotes a length of the sample.
- a speed of saturation can be computed as an image parameter according to the above Equation 15, which replaces a computed speed of darkening/lightening with an average saturation over time.
- a speed of object indicates a velocity of a motion object in the input image.
- the speed of object cannot be computed in a still image.
- the image parameter calculation unit 201 can compute the speed of object as an image parameter according to the following operations.
- An image is separated into a background and foreground, and an object is detected.
- a velocity can be computed using a magnitude of the motion.
- a speed of camera motion can be computed in the image as an image parameter.
- a skin contrast can be measured as an image parameter using a skin tone in the image.
- An operation of measuring the skin tone is similar to an operation of computing the global contrast, and may be performed as follows.
- the input image is determined to include a harsh tone, and when the difference is less than the reference value, the input image is determined to include a smooth tone.
- FIG. 5 illustrates an image enhancement method using automatic emotion detection according to an embodiment of the present invention.
- the image enhancement method analyzes a pixel value of each frame of an input image and automatically detects an emotional scale of the input image in operation S 501 . Then, a quality of the input image is enhanced based on an image mode selected according to the emotional scale in operation S 502 .
- the detecting of the emotional scale includes calculating at least one image parameter using the analyzed pixel value in operation S 503 and computing a Z score of each of the at least one image parameter using image statistical data in operation S 504 .
- the calculating of the at least one image parameter may include performing a color space conversion with respect to the pixel value of the input image according to an image parameter to be calculated.
- the image parameter is a mathematical parameter representing a physical property of each of the frames of the input image.
- the computing of the Z score may compute the Z score using an average and a standard deviation of an image parameter of various images.
- the detecting of the emotional scale (operation S 501 ) may detect the emotional scale of the input image using the computed Z score and a Z score of an image parameter with respect to at least one predetermined emotional scale.
- the detecting of the emotional scale (operation S 501 ) may determine a difference between the computed Z score and an average Z score of all image parameters with respect to the at least one predetermined emotional scale, and detect an emotional scale having a minimum difference as the emotional scale of the input image.
- the enhancing of the quality of the input image includes selecting an image mode of the input image according to the emotional scale in operation S 505 , and adjusting an image factor of the input image using an image factor adjustment parameter according to the image mode in operation S 506 .
- the selecting of the image mode may include selecting the image mode of the input image based on an image mode corresponding to a predetermined emotional scale.
- the adjusting adjusting of the image factor may adjust a lightness, a contrast, and/or a saturation of the input image using the image factor adjustment parameter according to the image mode.
- aspects of the present invention may be embodied in a computer-readable media including program instructions to implement various operations embodied by a computer.
- the media may also include, alone or in combination with the program instructions, data files, data structures, and the like.
- the media and program instructions may be those specially designed and constructed for the purposes the example embodiment of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts.
- Examples of computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media, for example, CD ROM disks and DVD, magneto-optical media, for example, optical disks, and hardware devices that may be specially configured to store and perform program instructions, for example, read-only memory (ROM), random access memory (RAM), flash memory, and the like.
- ROM read-only memory
- RAM random access memory
- aspects of the present invention may also be realized as a data signal embodied in a carrier wave and comprising a program readable by a computer and transmittable over the Internet.
- Examples of program instructions include both machine code, for example, produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter.
- the described hardware devices may be configured to act as one or more software modules in order to perform the operations of the above-described example embodiments of the present invention.
Abstract
Description
where Zj denotes a Z score with respect to each image parameter, Vj denotes each computed image parameter, and Vj
where Zj denotes the computed Z score, Zj,k
where dacout and dacin denote any one of an output and input RGB of a current pixel, and Mlum′ denotes a corrected average luminance value. When dacout is less than 0, (for example, −2) dacout may be set as 0. When dacout is greater than 255, (for example, 260) dacout may be set as 255. When dacout is from 0 to 255, dacout may be maintained as is. Each constant can vary according to the configuration of the
dac out =dac in +p, [Equation 4]
where dacout and dacin denote any one of the output and input R, G, B of the current pixel, and p denotes the image factor adjustment parameter. When dacout is less than 0, dacout can be set as 0. When dacout is greater than 255, dacout can be set as 255. Also, when dacout is from 0 to 255, dacout can be maintained as is.
where Mlum denotes the average luminance, n and m denote width and length of an image, respectively, i and j denote a horizontal location and a vertical location of a pixel, respectively, Y is a value where an R, G, B value of the input image is converted into a luminance value, and a, b, c, and d are constants.
where k denotes a size of a kernel, i and j denote a horizontal location and a vertical location of a pixel, respectively, and p denotes an R, G, B value.
where Msat denotes the average saturation for each frame of the input image, n and m denote the width and length of the image, respectively, i and j denote the horizontal location and vertical location of a pixel, respectively, and S denotes a saturation value of a pixel located in (i, j).
d gc =M lum,hi −M lum,lo, [Equation 9]
where dgc denotes the global contrast, Mlum,hi denotes an average luminance of pixels having a luminance value greater than an overall average luminance for each frame of the input image, and Mlum,lo denotes an average luminance of pixels having a luminance value less than the overall average luminance for each frame of the input image.
d gsc =M sat,hi −M sat,lo, [Equation 10]
where dgsc denotes the global saturation contrast, Msat,hi denotes an average saturation value of pixels having a saturation value greater than an overall average saturation value for each frame of the input image, and Msat,lo denotes an average saturation value of pixels having a saturation value less than an overall average saturation value for each frame of the input image.
where the color balance reflects whether the input image has a cool or warm appearance. For example, the color balance indicates a color temperature closest to an average chromaticity (x, y), after mathematically averaging CIE 1931 tristmulus values of pixels using an sRGB color space conversion. Referring to Equation 11, p denotes an R, G, B value of an input pixel, and a, b, c, d, e, f, g, h, and i denote constants. For example, a, b, c, d, e, f, g, h, and i can be 41.24, 35.76, 18.05, 21.26, 71.52, 7.22, 1.93, 11.92, and 95.05, respectively. Furthermore,
where T denotes the color temperature, XPI(T) and YPI(T) denote the color temperature of the input image, and
where c denotes a number of high frequency components in the DC transformed image from among each pixel of the input image, the number of high frequency components is greater than 32, and sizeDCT denotes a size of the DC transformed image.
where Nsh denotes a number of sharp segments, and Nbi denotes a number of blurred segments. For example, an image can be segmented into a segment of n*n size.
where m′(i) denotes a numerical derivative of m(i), i denotes a number of samples in a clip, and n denotes a length of the sample. When the clip includes a dark area, M is a negative number, and when the clip includes a light area, M is a positive number.
-
- (1) It is assumed that a display device displays the image in an sRGB color space. A CIEXYZ value is determined first using a gamma value, and the sRGB color space is converted into an XYZ color space by a conversion matrix. The above operation is referred to as an operation of computing the color balance.
- (2) A CIE L*a*b value is determined using a sum of rows of the sRGB conversion matrix.
- (3) When L* is greater than 30, hue is between 18 and 80, and saturation (Cab*) is between 10 and 30, a pixel is considered as the skin tone and remaining pixels are ignored.
Claims (36)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR2007-125194 | 2007-12-04 | ||
KR1020070125194A KR101390202B1 (en) | 2007-12-04 | 2007-12-04 | System and method for enhancement image using automatic emotion detection |
KR10-2007-0125194 | 2007-12-04 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20090141983A1 US20090141983A1 (en) | 2009-06-04 |
US8224106B2 true US8224106B2 (en) | 2012-07-17 |
Family
ID=40675783
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/166,676 Active 2031-05-17 US8224106B2 (en) | 2007-12-04 | 2008-07-02 | Image enhancement system and method using automatic emotion detection |
Country Status (2)
Country | Link |
---|---|
US (1) | US8224106B2 (en) |
KR (1) | KR101390202B1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120023135A1 (en) * | 2009-11-11 | 2012-01-26 | Erik Dahlkvist | Method for using virtual facial expressions |
US20130083052A1 (en) * | 2011-09-30 | 2013-04-04 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
US20130148894A1 (en) * | 2010-08-31 | 2013-06-13 | Mariko Yamamoto | Image reconstruction method and device |
US8863619B2 (en) | 2011-05-11 | 2014-10-21 | Ari M. Frank | Methods for training saturation-compensating predictors of affective response to stimuli |
US9015084B2 (en) | 2011-10-20 | 2015-04-21 | Gil Thieberger | Estimating affective response to a token instance of interest |
US9134816B2 (en) | 2009-11-11 | 2015-09-15 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
WO2016023526A1 (en) * | 2014-08-14 | 2016-02-18 | 腾讯科技(深圳)有限公司 | Method and device for video enhancement |
US9449521B2 (en) | 2009-11-11 | 2016-09-20 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
US10949461B2 (en) | 2016-04-18 | 2021-03-16 | International Business Machines Corporation | Composable templates for managing disturbing image and sounds |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8184869B2 (en) * | 2008-05-30 | 2012-05-22 | Hewlett-Packard Development Company, L.P. | Digital image enhancement |
US8606733B2 (en) * | 2009-12-07 | 2013-12-10 | Xerox Corporation | System and method for classification and selection of color palettes |
US20130097176A1 (en) * | 2011-10-12 | 2013-04-18 | Ensequence, Inc. | Method and system for data mining of social media to determine an emotional impact value to media content |
US9277375B2 (en) | 2012-09-28 | 2016-03-01 | Nokia Technologies Oy | Method and apparatus relating to a mood state of a user |
CN109191398B (en) * | 2018-08-29 | 2021-08-03 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and electronic equipment |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5676138A (en) * | 1996-03-15 | 1997-10-14 | Zawilinski; Kenneth Michael | Emotional response analyzer system with multimedia display |
KR19980087759A (en) | 1998-09-14 | 1998-12-05 | 김홍석 | Emotion Color Control Device of Image Display and Control Method thereof |
JP2005012285A (en) | 2003-06-16 | 2005-01-13 | Sharp Corp | Moving picture processing apparatus, moving picture processing program, and recording medium |
US20050168595A1 (en) | 2004-02-04 | 2005-08-04 | White Michael F. | System and method to enhance the quality of digital images |
JP2005235066A (en) | 2004-02-23 | 2005-09-02 | Seiko Epson Corp | Device, method and program of image correction |
KR20060039983A (en) | 2004-11-04 | 2006-05-10 | 한국전자통신연구원 | Apparatus and method for prediction of image reality |
JP2006173856A (en) | 2004-12-14 | 2006-06-29 | Seiko Epson Corp | Automatic image corrector and electronic apparatus |
KR20070055925A (en) | 2005-11-28 | 2007-05-31 | 엘지전자 주식회사 | Method and apparatus for controlling a colour of (an) image display device |
US20070291334A1 (en) * | 2006-06-20 | 2007-12-20 | Fujifilm Corporation | Imaging apparatus |
US20080091515A1 (en) * | 2006-10-17 | 2008-04-17 | Patentvc Ltd. | Methods for utilizing user emotional state in a business process |
US20080260212A1 (en) * | 2007-01-12 | 2008-10-23 | Moskal Michael D | System for indicating deceit and verity |
US7751599B2 (en) * | 2006-08-09 | 2010-07-06 | Arcsoft, Inc. | Method for driving virtual facial expressions by automatically detecting facial expressions of a face image |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0734474U (en) * | 1993-12-09 | 1995-06-23 | 富士通テン株式会社 | Liquid crystal display |
KR20070091853A (en) * | 2006-03-07 | 2007-09-12 | 삼성전자주식회사 | Apparatus and method for reproducting color image-adaptively |
-
2007
- 2007-12-04 KR KR1020070125194A patent/KR101390202B1/en active IP Right Grant
-
2008
- 2008-07-02 US US12/166,676 patent/US8224106B2/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5676138A (en) * | 1996-03-15 | 1997-10-14 | Zawilinski; Kenneth Michael | Emotional response analyzer system with multimedia display |
KR19980087759A (en) | 1998-09-14 | 1998-12-05 | 김홍석 | Emotion Color Control Device of Image Display and Control Method thereof |
JP2005012285A (en) | 2003-06-16 | 2005-01-13 | Sharp Corp | Moving picture processing apparatus, moving picture processing program, and recording medium |
US20050168595A1 (en) | 2004-02-04 | 2005-08-04 | White Michael F. | System and method to enhance the quality of digital images |
JP2005235066A (en) | 2004-02-23 | 2005-09-02 | Seiko Epson Corp | Device, method and program of image correction |
KR20060039983A (en) | 2004-11-04 | 2006-05-10 | 한국전자통신연구원 | Apparatus and method for prediction of image reality |
JP2006173856A (en) | 2004-12-14 | 2006-06-29 | Seiko Epson Corp | Automatic image corrector and electronic apparatus |
KR20070055925A (en) | 2005-11-28 | 2007-05-31 | 엘지전자 주식회사 | Method and apparatus for controlling a colour of (an) image display device |
US20070291334A1 (en) * | 2006-06-20 | 2007-12-20 | Fujifilm Corporation | Imaging apparatus |
US7751599B2 (en) * | 2006-08-09 | 2010-07-06 | Arcsoft, Inc. | Method for driving virtual facial expressions by automatically detecting facial expressions of a face image |
US20080091515A1 (en) * | 2006-10-17 | 2008-04-17 | Patentvc Ltd. | Methods for utilizing user emotional state in a business process |
US20080260212A1 (en) * | 2007-01-12 | 2008-10-23 | Moskal Michael D | System for indicating deceit and verity |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120023135A1 (en) * | 2009-11-11 | 2012-01-26 | Erik Dahlkvist | Method for using virtual facial expressions |
US9449521B2 (en) | 2009-11-11 | 2016-09-20 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
US9134816B2 (en) | 2009-11-11 | 2015-09-15 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
US20130148894A1 (en) * | 2010-08-31 | 2013-06-13 | Mariko Yamamoto | Image reconstruction method and device |
US9129187B2 (en) * | 2010-08-31 | 2015-09-08 | Hitachi Medical Corporation | Image reconstruction method and device |
US9076108B2 (en) | 2011-05-11 | 2015-07-07 | Ari M. Frank | Methods for discovering and classifying situations that influence affective response |
US8938403B2 (en) | 2011-05-11 | 2015-01-20 | Ari M. Frank | Computing token-dependent affective response baseline levels utilizing a database storing affective responses |
US8965822B2 (en) | 2011-05-11 | 2015-02-24 | Ari M. Frank | Discovering and classifying situations that influence affective response |
US8918344B2 (en) | 2011-05-11 | 2014-12-23 | Ari M. Frank | Habituation-compensated library of affective response |
US8898091B2 (en) | 2011-05-11 | 2014-11-25 | Ari M. Frank | Computing situation-dependent affective response baseline levels utilizing a database storing affective responses |
US8886581B2 (en) | 2011-05-11 | 2014-11-11 | Ari M. Frank | Affective response predictor for a stream of stimuli |
US8863619B2 (en) | 2011-05-11 | 2014-10-21 | Ari M. Frank | Methods for training saturation-compensating predictors of affective response to stimuli |
US9183509B2 (en) | 2011-05-11 | 2015-11-10 | Ari M. Frank | Database of affective response and attention levels |
US9230220B2 (en) | 2011-05-11 | 2016-01-05 | Ari M. Frank | Situation-dependent libraries of affective response |
US20130083052A1 (en) * | 2011-09-30 | 2013-04-04 | Erik Dahlkvist | Method for using virtual facial and bodily expressions |
US9015084B2 (en) | 2011-10-20 | 2015-04-21 | Gil Thieberger | Estimating affective response to a token instance of interest |
WO2016023526A1 (en) * | 2014-08-14 | 2016-02-18 | 腾讯科技(深圳)有限公司 | Method and device for video enhancement |
US10390014B2 (en) | 2014-08-14 | 2019-08-20 | Tencent Technology (Shenzhen) Company Limited | Video enhancement method and device |
US11109029B2 (en) | 2014-08-14 | 2021-08-31 | Tencent Technology (Shenzhen) Company Limited | Video enhancement method and device |
US10949461B2 (en) | 2016-04-18 | 2021-03-16 | International Business Machines Corporation | Composable templates for managing disturbing image and sounds |
US11086928B2 (en) | 2016-04-18 | 2021-08-10 | International Business Machines Corporation | Composable templates for managing disturbing image and sounds |
Also Published As
Publication number | Publication date |
---|---|
US20090141983A1 (en) | 2009-06-04 |
KR20090058425A (en) | 2009-06-09 |
KR101390202B1 (en) | 2014-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8224106B2 (en) | Image enhancement system and method using automatic emotion detection | |
Liu et al. | CID: IQ–a new image quality database | |
JP5389903B2 (en) | Optimal video selection | |
US7283666B2 (en) | Digital image exposure correction | |
US7711210B2 (en) | Selection of images for image processing | |
US7840084B2 (en) | Digital camera incorporating a sharpness predictor | |
US8666156B2 (en) | Image-based backgrounds for images | |
US7663636B2 (en) | Apparatus and method for automatically analyzing digital video quality | |
US6249601B1 (en) | Method for determining color of illuminant and apparatus therefor | |
JP2004194342A (en) | User's preference data generation method and unit relevant to video color characteristic and video color preference characteristic conversion method and unit using the same | |
EP3136723A1 (en) | Image processing apparatus | |
KR102567860B1 (en) | Improved inverse tone mapping method and corresponding device | |
US9087385B2 (en) | Method for improving images captured underwater | |
US9418410B2 (en) | Image processing apparatus and method thereof | |
JP2006197630A (en) | Apparatus and method for adaptively controlling luminance of image, and computer-readable recording medium | |
JP2006091980A5 (en) | ||
El Khoury et al. | Color and sharpness assessment of single image dehazing | |
US8995759B2 (en) | Image processing apparatus and image processing method | |
JP2004201314A (en) | Apparatus and method for reproducing skin color in image signal | |
JP2007304948A (en) | Image quality objective evaluation device and method | |
KR101769543B1 (en) | Apparatus and method for improving image resolution using sharpness and color saturation | |
JP2008178095A (en) | Video image classification method based on attribute of video image, system and storing medium | |
JP2012083848A (en) | Image processing device, image processing method, imaging device, and image processing program | |
US7986852B2 (en) | Image processing apparatus and method for adjusting a lightness and an input image | |
US20140198256A1 (en) | Image processing apparatus and associated method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SAMSUNG ELECTRONICS CO., LTD., KOREA, REPUBLIC OF Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BING, HAN;BODROGI, PETER;PARK, DU-SIK;AND OTHERS;REEL/FRAME:021251/0656 Effective date: 20080619 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 8 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |